a serious "compare CSE" issue that is nontrivial to get right,

but which is responsible for us doing really bad things to 256.bzip2.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@126126 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/X86/README.txt b/lib/Target/X86/README.txt
index 1e1660dbca0108e363911b0e115fc641defbb81b..abd1515cf5d700044fb5ab7333702f6cf58f47f1 100644 (file)
--- a/lib/Target/X86/README.txt
+++ b/lib/Target/X86/README.txt
@@ -1878,3 +1878,72 @@ _add32carry:
        ret
 
 //===---------------------------------------------------------------------===//
+
+The hot loop of 256.bzip2 contains code that looks a bit like this:
+
+int foo(char *P, char *Q, int x, int y) {
+  if (P[0] != Q[0])
+     return P[0] < Q[0];
+  if (P[1] != Q[1])
+     return P[1] < Q[1];
+  if (P[2] != Q[2])
+     return P[2] < Q[2];
+   return P[3] < Q[3];
+}
+
+In the real code, we get a lot more wrong than this.  However, even in this
+code we generate:
+
+_foo:                                   ## @foo
+## BB#0:                                ## %entry
+       movb    (%rsi), %al
+       movb    (%rdi), %cl
+       cmpb    %al, %cl
+       je      LBB0_2
+LBB0_1:                                 ## %if.then
+       cmpb    %al, %cl
+       jmp     LBB0_5
+LBB0_2:                                 ## %if.end
+       movb    1(%rsi), %al
+       movb    1(%rdi), %cl
+       cmpb    %al, %cl
+       jne     LBB0_1
+## BB#3:                                ## %if.end38
+       movb    2(%rsi), %al
+       movb    2(%rdi), %cl
+       cmpb    %al, %cl
+       jne     LBB0_1
+## BB#4:                                ## %if.end60
+       movb    3(%rdi), %al
+       cmpb    3(%rsi), %al
+LBB0_5:                                 ## %if.end60
+       setl    %al
+       movzbl  %al, %eax
+       ret
+
+Note that we generate jumps to LBB0_1 which does a redundant compare.  The
+redundant compare also forces the register values to be live, which prevents
+folding one of the loads into the compare.  In contrast, GCC 4.2 produces:
+
+_foo:
+       movzbl  (%rsi), %eax
+       cmpb    %al, (%rdi)
+       jne     L10
+L12:
+       movzbl  1(%rsi), %eax
+       cmpb    %al, 1(%rdi)
+       jne     L10
+       movzbl  2(%rsi), %eax
+       cmpb    %al, 2(%rdi)
+       jne     L10
+       movzbl  3(%rdi), %eax
+       cmpb    3(%rsi), %al
+L10:
+       setl    %al
+       movzbl  %al, %eax
+       ret
+
+which is "perfect".
+
+//===---------------------------------------------------------------------===//
+